It has always been very difficult to recognize realistic actions from unconstrained videos because there are tremendous variations from camera motion, background clutter, object a...
We propose an approach to incorporating dynamic models into the human body tracking process that yields full 3– D reconstructions from monocular sequences. We formulate the trac...
See a PPT file with videos at www.research.microsoft.com/users/jojic/FlexiblesSprites.htm We propose a technique for automatically learning layers of "flexible sprites" ...
This paper presents a method to recover the full-motion (3 rotations and 3 translations) of the head from an input video using a cylindrical head model. Given an initial reference...
We describe a method for registering and superresolving moving vehicles from aerial surveillance video. The challenge of vehicle super-resolution lies in the fact that vehicles ma...